Search Results

As I understand how a stateful LSTM works, I could divide my 100 training examples into 4 sequences of 25 examples. … How would I deal with the state of the LSTM when doing so? …

As far as I understand the follwoing two models are essentially identical: Having a stateful LSTM with just a single time step and passing 10 time-series data points into it one by one, and using the … final output as the prediction for the 11th data point Having a stateless LSTM unrolled into 10 time steps passing the entire 10 data points as input to the corresponding time steps, then using the output …

My LSTM takes in as input batches of shape (50, 25, 108). … the state of the LSTM is reset. …

I am building an LSTM, to attempt to learn the trend historic trend of some time-series data set (e.g. the daily share price of a company). … I am using a stateful LSTM and hence taking the output state of one batch and inputting it to the state of the next batch, does this mean that my next batch must be [t=25, t=49]? …

Now, in a hope to become more familiar with implementing my NNs using TensorFlow, I have decided to write an LSTM using it. … The LSTM I am trying to implement is the well-known example of learning from the entire works of Shakespeare, and then producing its own text in the same style. …

Say I have a time series data set of 100 sequential timesteps, and I want to train and test an LSTM on the data set, but only on forecasting a single timestep into the future. … Otherwise, by the nature of how an LSTM works, can I train on the first 80 data points, and then pass in the full length 100 sequence and use the predictions at timesteps 81 - 100 as the test set predictions …

I have written an LSTM using Tensorflow that reads in sequences of 25 chars from a large text file of Shakespeare's plays. All charatcers are encoded to and from one-hot vectors. …

Take for example, I am building an LSTM RNN which takes in 5 features that correlate to the number of sales of a product for that day. … The LSTM takes in sequences of 10 days of these 5 features (it is unrolled to 10 time steps, each receiving 5 features as input), and then attempts to predict the number of sales for the 11th day. …

I build an LSTM that takes in two hours of these sequential data points (24 time steps) and then attempts to predict if the price will have increased/decreased an hour after the last data point fed into … As the LSTM produces an output at each time step, should I be calculating the loss from all 24 of these outputs, or just the last one?. …